
Version 2.0 update:
after I connected the grid pattern sometimes visible in bright or dark parts of the images with the fp4 training with OneTrainer, I switched to fp8 training, which got rid of the pattern. But I have to redo all my LoRAs to fix them all and i did some minor corrections on the dataset. Nothing changed in usage, except the tag is now <lora:WireframeGlasses-SmallRectangular-step01280:1>.
Flux seems pretty limited if you want glasses - mostly the more round sort with a thicker frame. I intended to make a all-in-one LoRA first, but that didn't work - if you want to specify between normal and small glasses, round, rectangular and oval shapes you had to train each one separately.
This creates small rectangular wire-frame glasses - to acquire my dataset, I had to make some kind of internet archaeology, going back in the late 2000's when those were in vogue for a small period of time.
Albeit not strictly neccessary, a <lora:WireframeGlasses-rectangularSmall-50:1> tag increases the influence. It has also the potential of creating several colors, like the blue one in the example set.
描述:
Version 2.0 is trained with fp8, getting rid of the grid pattern sometimes visible in the images. The dataset was slightly expanded.
训练词语: small rectangular wire-frame glasses
名称: WireframeGlasses-RectangularSmall-step01280.safetensors
大小 (KB): 37502
类型: Model
Pickle 扫描结果: Success
Pickle 扫描信息: No Pickle imports
病毒扫描结果: Success